import py import os import inspect from py.__.apigen.layout import LayoutPage from py.__.apigen.source import browser as source_browser from py.__.apigen.source import html as source_html from py.__.apigen.source import color as source_color from py.__.apigen.tracer.description import is_private from py.__.apigen.rest.genrest import split_of_last_part from py.__.apigen.linker import relpath from py.__.apigen.html import H reversed = py.builtin.reversed sorted = py.builtin.sorted html = py.xml.html raw = py.xml.raw REDUCE_CALLSITES = True def find_method_origin(meth): cls = getattr(meth, 'im_class', None) if cls is None: return None # XXX unknown origin (built-in function or method or sth) name = meth.im_func.func_name origin = cls # XXX old-style classes support required? :| mro = inspect.getmro(cls) for base in mro: m = getattr(base, name, None) if m is None: continue if not hasattr(m, 'im_func'): # builtin return None if m.im_func is meth.im_func: origin = base return origin def is_navigateable(name): return (not is_private(name) and name != '__doc__') def show_property(name): if not name.startswith('_'): return True if name.startswith('__') and name.endswith('__'): # XXX do we need to skip more manually here? if (name not in dir(object) and name not in ['__doc__', '__dict__', '__name__', '__module__', '__weakref__', '__apigen_hide_from_nav__']): return True return False def deindent(str, linesep='\n'): """ de-indent string can be used to de-indent Python docstrings, it de-indents the first line to the side always, and determines the indentation of the rest of the text by taking that of the least indented (filled) line """ lines = str.strip().split(linesep) normalized = [] deindent = None normalized.append(lines[0].strip()) # replace tabs with spaces, empty lines that contain spaces only, and # find out what the smallest indentation is for line in lines[1:]: line = line.replace('\t', ' ' * 4) stripped = line.strip() if not stripped: normalized.append('') else: rstripped = line.rstrip() indent = len(rstripped) - len(stripped) if deindent is None or indent < deindent: deindent = indent normalized.append(line) ret = [normalized[0]] for line in normalized[1:]: if not line: ret.append(line) else: ret.append(line[deindent:]) return '%s\n' % (linesep.join(ret),) def get_linesep(s, default='\n'): """ return the line seperator of a string returns 'default' if no seperator can be found """ for sep in ('\r\n', '\r', '\n'): if sep in s: return sep return default def get_param_htmldesc(linker, func): """ get the html for the parameters of a function """ import inspect # XXX copy and modify formatargspec to produce html return inspect.formatargspec(*inspect.getargspec(func)) # some helper functionality def source_dirs_files(fspath, fil=None): """ returns a tuple (dirs, files) for fspath dirs are all the subdirs, files are the files which are interesting in building source documentation for a Python code tree (basically all normal files excluding .pyc and .pyo ones) all files and dirs that have a name starting with . are considered hidden """ dirs = [] files = [] for child in fspath.listdir(fil=fil): if child.basename.startswith('.'): continue if child.check(dir=True): dirs.append(child) elif child.check(file=True): if child.ext in ['.pyc', '.pyo']: continue files.append(child) return sorted(dirs), sorted(files) def create_namespace_tree(dotted_names): """ creates a tree (in dict form) from a set of dotted names """ ret = {} for dn in dotted_names: path = dn.split('.') for i in xrange(len(path)): ns = '.'.join(path[:i]) itempath = '.'.join(path[:i + 1]) if ns not in ret: ret[ns] = [] if itempath not in ret[ns]: ret[ns].append(itempath) return ret def wrap_page(project, title, targetpath, contentel, navel, basepath, pageclass): page = pageclass(project, title, targetpath, nav=navel, encoding='UTF-8') page.set_content(contentel) page.setup_scripts_styles(basepath) return page def enumerate_and_color(codelines, firstlineno, enc): snippet = H.SourceBlock() tokenizer = source_color.Tokenizer(source_color.PythonSchema) for i, line in enumerate(codelines): try: snippet.add_line(i + firstlineno + 1, source_html.prepare_line([line], tokenizer, enc)) except py.error.ENOENT: # error reading source code, giving up snippet = codelines break return snippet def enumerate_and_color_module(path, enc): snippet = H.SourceBlock() tokenizer = source_color.Tokenizer(source_color.PythonSchema) for i, text in enumerate(source_html.prepare_module(path, tokenizer, enc)): snippet.add_line(i + 1, text) return snippet _get_obj_cache = {} def get_obj(dsa, pkg, dotted_name): full_dotted_name = '%s.%s' % (pkg.__name__, dotted_name) if dotted_name == '': return pkg try: return _get_obj_cache[dotted_name] except KeyError: pass path = dotted_name.split('.') ret = pkg for item in path: marker = [] ret = getattr(ret, item, marker) if ret is marker: try: ret = dsa.get_obj(dotted_name) except KeyError: raise NameError('can not access %s in %s' % (item, full_dotted_name)) else: break _get_obj_cache[dotted_name] = ret return ret def get_rel_sourcepath(projpath, filename, default=None): relpath = py.path.local(filename).relto(projpath) if not relpath: return default return relpath def get_package_revision(packageroot, _revcache={}): try: rev = _revcache[packageroot] except KeyError: wc = py.path.svnwc(packageroot) rev = None if wc.check(versioned=True): rev = py.path.svnwc(packageroot).info().rev _revcache[packageroot] = rev if packageroot.basename == "py": assert rev is not None return rev # the PageBuilder classes take care of producing the docs (using the stuff # above) class AbstractPageBuilder(object): pageclass = LayoutPage def write_page(self, title, reltargetpath, tag, nav): targetpath = self.base.join(reltargetpath) relbase= relpath('%s%s' % (targetpath.dirpath(), targetpath.sep), self.base.strpath + '/') page = wrap_page(self.project, title, targetpath, tag, nav, self.base, self.pageclass) # we write the page with _temporary_ hrefs here, need to be replaced # from the TempLinker later content = page.unicode() targetpath.ensure() targetpath.write(content.encode("utf8")) class SourcePageBuilder(AbstractPageBuilder): """ builds the html for a source docs page """ def __init__(self, base, linker, projroot, project, capture=None, pageclass=LayoutPage, dirfilter=None): self.base = base self.linker = linker self.projroot = projroot self.project = project self.capture = capture self.pageclass = pageclass self.dirfilter = dirfilter def build_navigation(self, fspath): nav = H.Navigation(class_='sidebar') relpath = fspath.relto(self.projroot) path = relpath.split(os.path.sep) indent = 0 # build links to parents if relpath != '': for i in xrange(len(path)): dirpath = os.path.sep.join(path[:i]) abspath = self.projroot.join(dirpath).strpath if i == 0: text = self.projroot.basename else: text = path[i-1] nav.append(H.NavigationItem(self.linker, abspath, text, indent, False)) indent += 1 # build siblings or children and self if fspath.check(dir=True): # we're a dir, build ourselves and our children dirpath = fspath nav.append(H.NavigationItem(self.linker, dirpath.strpath, dirpath.basename, indent, True)) indent += 1 elif fspath.strpath == self.projroot.strpath: dirpath = fspath else: # we're a file, build our parent's children only dirpath = fspath.dirpath() diritems, fileitems = source_dirs_files(dirpath, self.dirfilter) for dir in diritems: nav.append(H.NavigationItem(self.linker, dir.strpath, dir.basename, indent, False)) for file in fileitems: selected = (fspath.check(file=True) and file.basename == fspath.basename) nav.append(H.NavigationItem(self.linker, file.strpath, file.basename, indent, selected)) return nav re = py.std.re _reg_body = re.compile(r'
]*>(.*)', re.S) def build_python_page(self, fspath): # XXX two reads of the same file here... not very bad (disk caches # and such) but also not very nice... enc = source_html.get_module_encoding(fspath.strpath) try: colored = [enumerate_and_color_module(fspath, enc)] except (KeyboardInterrupt, SystemExit): raise except Exception, e: #self.capture.err.writeorg('\ncompilation exception: %s\n' % (e,)) # problem building HTML with anchors; let's try without... source = fspath.read() sep = get_linesep(source) colored = [enumerate_and_color(source.split(sep), 0, enc)] tag = H.PythonSource(colored) nav = self.build_navigation(fspath) return tag, nav def build_dir_page(self, fspath): dirs, files = source_dirs_files(fspath, self.dirfilter) dirs = [(p.basename, self.linker.get_lazyhref(str(p))) for p in dirs] files = [(p.basename, self.linker.get_lazyhref(str(p))) for p in files] tag = H.DirList(dirs, files) nav = self.build_navigation(fspath) return tag, nav def build_nonpython_page(self, fspath): try: tag = H.NonPythonSource(unicode(fspath.read(), 'utf-8')) except UnicodeError: tag = H.NonPythonSource('no source available (binary file?)') nav = self.build_navigation(fspath) return tag, nav def build_pages(self, base): def visit(p): dirs, files = source_dirs_files(p, self.dirfilter) for d in dirs: yield d for sp in visit(d): yield sp for f in files: yield f for fspath in [base] + list(visit(base)): if fspath.ext in ['.pyc', '.pyo']: continue if self.capture: self.capture.err.writeorg('.') relfspath = fspath.relto(base) if relfspath.find('%s.' % (os.path.sep,)) > -1: # skip hidden dirs and files continue elif fspath.check(dir=True): if relfspath != '': relfspath += os.path.sep reloutputpath = 'source%s%sindex.html' % (os.path.sep, relfspath) else: reloutputpath = "source%s%s.html" % (os.path.sep, relfspath) reloutputpath = reloutputpath.replace(os.path.sep, '/') outputpath = self.base.join(reloutputpath) self.linker.set_link(str(fspath), reloutputpath) self.build_page(fspath, outputpath, base) def build_page(self, fspath, outputpath, base): """ build syntax-colored source views """ if fspath.check(ext='.py'): try: tag, nav = self.build_python_page(fspath) except (KeyboardInterrupt, SystemExit): raise except: # XXX strange stuff going wrong at times... need to fix raise exc, e, tb = py.std.sys.exc_info() print '%s - %s' % (exc, e) print print ''.join(py.std.traceback.format_tb(tb)) print '-' * 79 del tb tag, nav = self.build_nonpython_page(fspath) elif fspath.check(dir=True): tag, nav = self.build_dir_page(fspath) else: tag, nav = self.build_nonpython_page(fspath) title = 'sources for %s' % (fspath.basename,) rev = self.get_revision(fspath) if rev: title += ' [rev. %s]' % (rev,) reltargetpath = outputpath.relto(self.base).replace(os.path.sep, '/') self.write_page(title, reltargetpath, tag, nav) _revcache = {} def get_revision(self, path): return get_package_revision(self.projroot) strpath = path.strpath if strpath in self._revcache: return self._revcache[strpath] wc = py.path.svnwc(path) if wc.check(versioned=True): rev = wc.info().created_rev else: rev = None self._revcache[strpath] = rev return rev class ApiPageBuilder(AbstractPageBuilder): """ builds the html for an api docs page """ def __init__(self, base, linker, dsa, projroot, namespace_tree, project, capture=None, pageclass=LayoutPage): self.base = base self.linker = linker self.dsa = dsa self.projroot = projroot self.projpath = py.path.local(projroot) self.namespace_tree = namespace_tree self.project = project self.capture = capture self.pageclass = pageclass pkgname = self.dsa.get_module_name().split('/')[-1] self.pkg = __import__(pkgname) def build_callable_view(self, dotted_name): """ build the html for a class method """ # XXX we may want to have seperate func = get_obj(self.dsa, self.pkg, dotted_name) docstring = func.__doc__ if docstring: docstring = deindent(docstring) localname = func.__name__ argdesc = get_param_htmldesc(self.linker, func) excdesc = self.build_exception_description(dotted_name) valuedesc = self.build_callable_signature_description(dotted_name) sourcefile = inspect.getsourcefile(func) callable_source = self.dsa.get_function_source(dotted_name) # i assume they're both either available or unavailable(XXX ?) is_in_pkg = self.is_in_pkg(sourcefile) href = None text = 'could not get to source file' colored = [] if sourcefile and callable_source: enc = source_html.get_module_encoding(sourcefile) sep = get_linesep(callable_source) colored = [enumerate_and_color(callable_source.split(sep), func.func_code.co_firstlineno, enc)] relpath = get_rel_sourcepath(self.projroot, sourcefile, sourcefile) text = 'source: %s' % (relpath,) if is_in_pkg: href = self.linker.get_lazyhref(sourcefile, self.get_anchor(func)) csource = H.SourceSnippet(text, href, colored) cslinks = self.build_callsites(dotted_name) snippet = H.FunctionDescription(localname, argdesc, docstring, valuedesc, excdesc, csource, cslinks) return snippet def build_class_view(self, dotted_name): """ build the html for a class """ cls = get_obj(self.dsa, self.pkg, dotted_name) # XXX is this a safe check? try: sourcefile = inspect.getsourcefile(cls) except TypeError: sourcefile = None docstring = cls.__doc__ if docstring: docstring = deindent(docstring) if not hasattr(cls, '__name__'): clsname = 'instance of %s' % (cls.__class__.__name__,) else: clsname = cls.__name__ bases = self.build_bases(dotted_name) properties = self.build_properties(cls) methods = self.build_methods(dotted_name) if sourcefile is None: sourcelink = H.div('no source available') else: if sourcefile[-1] in ['o', 'c']: sourcefile = sourcefile[:-1] sourcelink = H.div(H.a('view source', href=self.linker.get_lazyhref(sourcefile, self.get_anchor(cls)))) snippet = H.ClassDescription( # XXX bases HTML H.ClassDef(clsname, bases, docstring, sourcelink, properties, methods), ) return snippet def build_bases(self, dotted_name): ret = [] bases = self.dsa.get_possible_base_classes(dotted_name) for base in bases: try: obj = self.dsa.get_obj(base.name) except KeyError: ret.append((base.name, None)) else: href = self.linker.get_lazyhref(base.name) ret.append((base.name, href)) return ret def build_properties(self, cls): properties = [] for attr in dir(cls): val = getattr(cls, attr) if show_property(attr) and not callable(val): if isinstance(val, property): val = '